# Mixtral 8x7B vs Qwen1.5-7B

> Qwen1.5-7B is the stronger model overall, scoring 30.8 to 26.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mixtral-8x7b-vs-qwen1-5-7b
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Mixtral 8x7B scores higher in 4 categories and Qwen1.5-7B in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5-7B leads 28.2 to 11.0.

## Snapshot

| | Mixtral 8x7B | Qwen1.5-7B |
|---|---|---|
| Provider | Mistral AI | Alibaba (Qwen) |
| Noometry Index | 26.8 | 30.8 |
| Rank | 328 | 270 |
| Context | 32K | — |
| Input $/M | $0.70 | — |
| Output $/M | $0.70 | — |
| Weights | Open | Open |

## Coding

- Mixtral 8x7B: 32.2 (#265)
- Qwen1.5-7B: 31.6 (#271)

| Benchmark | Mixtral 8x7B | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1127 | 1107 |
| HumanEval+ | 39.6% | — |
| MBPP+ | 49.7% | — |

## Reasoning

- Mixtral 8x7B: 17.4 (#283)
- Qwen1.5-7B: 19.5 (#237)

| Benchmark | Mixtral 8x7B | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1115 | 1066 |
| DTBench | 49.6% | — |
| Adversarial NLI | 55.2% | — |
| Epoch Capabilities Index | 118.38 | — |
| ForecastBench | 56.3 | — |
| HellaSwag | 86.7% | — |
| PIQA | 83.6% | — |
| WinoGrande | 77.2% | — |

## Math

- Mixtral 8x7B: 17.2 (#284)
- Qwen1.5-7B: 29.0 (#222)

| Benchmark | Mixtral 8x7B | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1147 | 1080 |
| Omni-MATH | 10.5% | — |
| MATH Level 5 | 10% | — |
| GSM8K | 74.4% | — |

## Knowledge

- Mixtral 8x7B: 11.0 (#296)
- Qwen1.5-7B: 28.2 (#239)

| Benchmark | Mixtral 8x7B | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | 1088 | 1055 |
| MMLU | 70.6% | 62.6% |
| GPQA Diamond | 30.6% | — |
| MMLU-Pro | 33.5% | — |
| GPQA (HELM) | 29.6% | — |
| ARC (AI2) Challenge | 87.3% | — |
| OpenBookQA | 85.8% | — |
| TriviaQA | 82.2% | — |

## Multilingual

- Mixtral 8x7B: 29.8 (#261)
- Qwen1.5-7B: 28.6 (#266)

| Benchmark | Mixtral 8x7B | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 1077 | 1058 |
| LMArena Chinese | 1055 | 1140 |
| LMArena Russian | 1090 | 1006 |
| LMArena French | 1165 | — |
| LMArena German | 1114 | — |
| LMArena Japanese | 931 | — |
| LMArena Korean | 968 | — |
| LMArena Spanish | 1110 | — |

## Instruction Following

- Mixtral 8x7B: 51.2 (#292)
- Qwen1.5-7B: 54.4 (#276)

| Benchmark | Mixtral 8x7B | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1110 | 1058 |
| IFEval | 57.5% | — |

## Long Context

- Mixtral 8x7B: 33.4 (#255)
- Qwen1.5-7B: 33.1 (#261)

| Benchmark | Mixtral 8x7B | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1103 | 1090 |

## Writing & Preference

- Mixtral 8x7B: 34.4 (#265)
- Qwen1.5-7B: 29.8 (#288)

| Benchmark | Mixtral 8x7B | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1132 | 1084 |
| LMArena Creative Writing | 1109 | 1035 |
| LMArena Multi-Turn | 1115 | 1061 |
| WildBench | 67.3% | — |

## FAQ

### Is Mixtral 8x7B better than Qwen1.5-7B?

Qwen1.5-7B is the stronger model overall, scoring 30.8 to 26.8 on the Noometry Index.

### Is Mixtral 8x7B or Qwen1.5-7B better for coding?

They score almost the same on coding (32.2 vs 31.6); test both on your own repository before choosing.

### How many benchmarks do Mixtral 8x7B and Qwen1.5-7B share?

13 benchmarks have published results for both models. Mixtral 8x7B has 38 scored results on Noometry and Qwen1.5-7B has 13.